Fraud Detection Model for Illegal Transactions
Journal of Computing and Social Informatics · 11.03.2024 · 3 (1) · 8-17
DOI: 10.33736/jcsi.6449.2024 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computing and Social Informatics, online erschienen am 11.03.2024. Verfasst von Musibau Adekunle Ibrahim und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Due to advancements in network technologies, digital security is becoming a top priority worldwide. This project aims to study how machine learning classifier such as random forest could be used to learn patterns in fraudulent and legitimate transactions in order to detect fraudulent transactions using Python programming language on Jupyter notebook as an Integrated Development Environment. Scikit-learn was used to develop algorithm, streamlit and heroku platforms for proper and efficient detection and classification of unauthorized transactions. This was incorporated into a web application that allows users to upload data that can be analyzed by the system to detect fraud. The Classification report and Confusion matrix have been used to evaluate each model’s accuracy. Random forest as a classifier model gave an accuracy of 99.95%. At the end of this study, a web-based application has been developed to upload data and detect fraudulent in online based transactions.
Zitieren
APA
Ibrahim, M. A., Ozoh, P., & Ojo, O. A. (2024). Fraud Detection Model for Illegal Transactions. Journal of Computing and Social Informatics, 3(1), 8-17. https://doi.org/10.33736/jcsi.6449.2024
Vancouver
Ibrahim MA, Ozoh P, Ojo OA. Fraud Detection Model for Illegal Transactions. Journal of Computing and Social Informatics. 2024;3(1):8-17. doi:10.33736/jcsi.6449.2024
BibTeX
@article{Ibrahim2024,
author = {Ibrahim, Musibau Adekunle and Ozoh, Patrick and Ojo, Oladotun Ayotunde},
title = {Fraud Detection Model for Illegal Transactions},
journal = {Journal of Computing and Social Informatics},
year = {2024},
volume = {3},
number = {1},
pages = {8--17},
doi = {10.33736/jcsi.6449.2024}
}
EUVIMED